Systematic comparison and prediction of the effects of missense mutations on protein-DNA and protein-RNA interactions

• DOI: 10.1371/journal.pcbi.1008951
• Publication Date: 2021-04-19T21:27:12Z
• Authors: Yao Jiang; Hui-Fang Liu; Rong Liu
• Keywords: Affinities

The binding affinities of protein-nucleic acid interactions could be altered due to missense mutations occurring in DNA- or RNA-binding proteins, therefore resulting various diseases. Unfortunately, a systematic comparison and prediction the effects on protein-DNA protein-RNA (these two mutation classes are termed MPDs MPRs, respectively) is still lacking. Here, we demonstrated that these generate similar different tendencies for free energy changes terms properties mutated residues. We then developed regression algorithms separately MPRs by introducing novel geometric partition-based features interface-based structural features. Through feature selection ensemble learning, computational frameworks integrated energy- nonenergy-based models were established estimate affinity from but selected final reflected specificity classes. Furthermore, proposed methodology was extended identification significantly decreased affinities. Extensive validations indicated our algorithm generally performed better than state-of-the-art methods both classification tasks. webserver software freely available at http://liulab.hzau.edu.cn/PEMPNI https://github.com/hzau-liulab/PEMPNI .